← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 (10c) · 32 GB · 4bit · 2026-05-06
Performance
1k
tokens
218.7
PP tok/s
13.5
TG tok/s
4682
TTFT (ms)
16.7
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 218.7 13.5 16.7 GB current
4k 213.7 13.1 18.1 GB view
Batching Results
Batch Size TG tok/s Speedup
13.5 1.00×
16.3 1.21×
20.7 1.53×